Default branch

dba1e27fa8 · llama: enable FA on CUDA CC 6.x GPUs (#16994) · Updated 2026-07-03 00:11:39 +00:00

Branches

d462a88c62 · chore: checkpoint agent tui updates · Updated 2026-07-03 07:08:16 +00:00

4
3

7c616f841b · fix the fixes · Updated 2026-07-02 23:14:01 +00:00

7
10

99d626a9bd · server: remove OLLAMA_EXPERIMENT=client2 · Updated 2026-06-29 23:55:10 +00:00

49
1

38a4f5bffc · update hermes docs · Updated 2026-06-29 19:43:12 +00:00

10
1

64bb0f9f61 · more styling · Updated 2026-06-29 18:40:25 +00:00

52
74

af0a0494d1 · address comments · Updated 2026-06-29 17:08:02 +00:00

19
4

4784290c9b · agent: use platform shell tool names · Updated 2026-06-27 00:26:38 +00:00

52
72

8568b3bdb2 · fix test · Updated 2026-06-26 16:19:16 +00:00

32
10

6e65d95ef5 · server: add cached eval metric to response · Updated 2026-06-25 23:21:08 +00:00

17
1

ce5dd77d44 · remove foreground flag · Updated 2026-06-25 19:38:07 +00:00

18
2

21bd899080 · update vscode docs · Updated 2026-06-25 19:01:56 +00:00

17
1

26e1549f96 · agent: harden compaction and tui state · Updated 2026-06-22 23:22:27 +00:00

52
39

5b7635b933 · docs: update glm references to glm-5.2 · Updated 2026-06-22 19:59:00 +00:00

41
1

289537a631 · redesigning two integrations page · Updated 2026-06-18 19:29:29 +00:00

43
5

0e8615db56 · Simplify MLX recommendation replacements · Updated 2026-06-17 23:30:01 +00:00

66
5

1b67929ade · Refine first-run prompt layout · Updated 2026-06-17 23:25:37 +00:00

52
2

6a6b975607 · ci: test darwin xcode pin · Updated 2026-06-17 19:08:27 +00:00

45
1

2228d8dbd7 · launch: address cloud recommendation review · Updated 2026-06-16 22:38:10 +00:00

52
2

05cb961273 · docs: update goose docs · Updated 2026-06-15 20:36:55 +00:00

50
2

4f5cc32150 · llm: fix context limit conditions · Updated 2026-06-13 01:03:05 +00:00

52
1